When I test with my dataset, can I use the image at different resolutions?

[Huangjianglu]

Thanks for your great job!
I want to use my own dataset during the test,but I find that there are errors due to different image resolutions.How should I change the model parameters to change the size of the input image resolution?

[JWSoh]

The model can be applied to any images with arbitrary resolution.
Would you please give me more information about the error?

[Huangjianglu]

Thanks for your reply!
When I test the code using my dataset,the following error occurred:

=============== Load Meta-trained Model parameters... ==============
Traceback (most recent call last):
File "main.py", line 68, in
main()
File "main.py", line 58, in main
_, pp =Tester(img, gt, img_path[i])
File "/media/omnisky/77177290-c7c1-4bcd-ace1-59e97a4df5d9/MZSR-master/test.py", line 89, in call
self.quick_test()
File "/media/omnisky/77177290-c7c1-4bcd-ace1-59e97a4df5d9/MZSR-master/test.py", line 194, in quick_test
self.sr = self.forward_pass(self.img, self.gt.shape)
File "/media/omnisky/77177290-c7c1-4bcd-ace1-59e97a4df5d9/MZSR-master/test.py", line 170, in forward_pass
ILR = imresize(input, self.scale, output_shape, self.upscale_method)
File "/media/omnisky/77177290-c7c1-4bcd-ace1-59e97a4df5d9/MZSR-master/imresize.py", line 40, in imresize
img_aug[:, sym_len_Hs:sym_len_Hs+in_H,:]=img
ValueError: could not broadcast input array from shape (3,64,64) into shape (3,34,64)

[JWSoh]

May be there could be a mismatch between the GT image shape and the scale.

Did you provide the ground-truth image?
If you don't have a ground-truth image for your dataset, you may provide an arbitrary image with the desired high-resolution shape.

[omidbazgirTTU]

I am also getting the same error as our friend @Huangjianglu is getting. I tried multiple images with different resolutions with the ground truth provided. They all give me the same error. Only in one case, the error was different (couldn't calculate the PSNR), but it also didn't save the output SR image. The saving SR image is before calculating the PSNR, so I expect it should at least save the output results.

[BassantTolba1234]

Dear Sir,
Amazing work ! Congratulation!!
please , I have a question.can you kindly provide me with the full path I should insert of checkpoint the trained large scale training model to be able to use it as a pre-trained to meta transfer training?
I'm waiting for your reply.
Thanks in advance

[784682065]

Thanks for your reply!
When I test the code using my dataset,the following error occurred:

=============== Load Meta-trained Model parameters... ==============
Traceback (most recent call last):
File "main.py", line 68, in
main()
File "main.py", line 58, in main
_, pp =Tester(img, gt, img_path[i])
File "/media/omnisky/77177290-c7c1-4bcd-ace1-59e97a4df5d9/MZSR-master/test.py", line 89, in call
self.quick_test()
File "/media/omnisky/77177290-c7c1-4bcd-ace1-59e97a4df5d9/MZSR-master/test.py", line 194, in quick_test
self.sr = self.forward_pass(self.img, self.gt.shape)
File "/media/omnisky/77177290-c7c1-4bcd-ace1-59e97a4df5d9/MZSR-master/test.py", line 170, in forward_pass
ILR = imresize(input, self.scale, output_shape, self.upscale_method)
File "/media/omnisky/77177290-c7c1-4bcd-ace1-59e97a4df5d9/MZSR-master/imresize.py", line 40, in imresize
img_aug[:, sym_len_Hs:sym_len_Hs+in_H,:]=img
ValueError: could not broadcast input array from shape (3,64,64) into shape (3,34,64)

Have you solved this problem? I am also getting it.

[BassantTolba1234]

Please @JWSoh I'm facing a problem when i load the pretrained model , specially when it reads the checkpoint
this is the error .. how did you kindly solve it please ??

NotFoundError (see above for traceback): Key MODEL/conv7/kernel/Adam_3 not found in checkpoint
[[Node: save/RestoreV2_69 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_69/tensor_names, save/RestoreV2_69/shape_and_slices)]]

[BassantTolba1234]

Please @784682065 I'm facing a problem when i load the pretrained model , specially when it reads the checkpoint
this is the error .. how did you kindly solve it please ??

NotFoundError (see above for traceback): Key MODEL/conv7/kernel/Adam_3 not found in checkpoint
[[Node: save/RestoreV2_69 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_69/tensor_names, save/RestoreV2_69/shape_and_slices)]]

[784682065]

Please @784682065 I'm facing a problem when i load the pretrained model , specially when it reads the checkpoint
this is the error .. how did you kindly solve it please ??

NotFoundError (see above for traceback): Key MODEL/conv7/kernel/Adam_3 not found in checkpoint
[[Node: save/RestoreV2_69 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_69/tensor_names, save/RestoreV2_69/shape_and_slices)]]

Sorry, I haven't encountered this problem.

[BassantTolba1234]

Thanks for your reply. mmm so do you have any tutorial or guidance i can follow? thanks in advance

…

On Mon, Dec 21, 2020 at 2:55 PM huzp ***@***.***> wrote: Please @784682065 <https://github.com/784682065> I'm facing a problem when i load the pretrained model , specially when it reads the checkpoint this is the error .. how did you kindly solve it please ?? NotFoundError (see above for traceback): Key MODEL/conv7/kernel/Adam_3 not found in checkpoint [[Node: save/RestoreV2_69 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_69/tensor_names, save/RestoreV2_69/shape_and_slices)]] Sorry, I haven't encountered this problem. — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#12 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AOE5CA5CUGZNFYXGVKMMP6LSV5ATRANCNFSM4N2QGD3Q> .